PyTorchKR Papers

최신 논문

총 4,806편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2406.08463

Self-supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinement

Visual localization techniques rely upon some underlying scene representation to localize against. These representations can be explicit such as 3D SFM map or implicit, such as a neural network that learns to encode the scene. The former requires sparse feature extractors and matchers to build the scene representation. The latter might lack geometric grounding not capturing the 3D structure of the scene well enough. This paper proposes to jointly learn the scene representation along with a 3D dense feature field and a 2D feature extractor whose outputs are embedded in the same metric space. Through a contrastive framework we align this volumetric field with the image-based extractor and regularize the latter with a ranking loss from learned surface information. We learn the underlying geometry of the scene with an implicit field through volumetric rendering and design our feature field to leverage intermediate geometric information encoded in the implicit field. The resulting features are discriminative and robust to viewpoint change while maintaining rich encoded information. Visual localization is then achieved by aligning the image-based features and the rendered volumetric features. We show the effectiveness of our approach on real-world scenes, demonstrating that our approach outperforms prior and concurrent work on leveraging implicit scene representations for localization.

arXiv:2406.08300

From Chaos to Clarity: 3DGS in the Dark

Novel view synthesis from raw images provides superior high dynamic range (HDR) information compared to reconstructions from low dynamic range RGB images. However, the inherent noise in unprocessed raw images compromises the accuracy of 3D scene representation. Our study reveals that 3D Gaussian Splatting (3DGS) is particularly susceptible to this noise, leading to numerous elongated Gaussian shapes that overfit the noise, thereby significantly degrading reconstruction quality and reducing inference speed, especially in scenarios with limited views. To address these issues, we introduce a novel self-supervised learning framework designed to reconstruct HDR 3DGS from a limited number of noisy raw images. This framework enhances 3DGS by integrating a noise extractor and employing a noise-robust reconstruction loss that leverages a noise distribution prior. Experimental results show that our method outperforms LDR/HDR 3DGS and previous state-of-the-art (SOTA) self-supervised and supervised pre-trained models in both reconstruction quality and inference speed on the RawNeRF dataset across a broad range of training views. Code can be found in \url{https://lizhihao6.github.io/Raw3DGS}.

arXiv:2406.07986공식 코드 · Papers with Code

SimSAM: Simple Siamese Representations Based Semantic Affinity Matrix for Unsupervised Image Segmentation

Recent developments in self-supervised learning (SSL) have made it possible to learn data representations without the need for annotations. Inspired by the non-contrastive SSL approach (SimSiam), we introduce a novel framework SIMSAM to compute the Semantic Affinity Matrix, which is significant for unsupervised image segmentation. Given an image, SIMSAM first extracts features using pre-trained DINO-ViT, then projects the features to predict the correlations of dense features in a non-contrastive way. We show applications of the Semantic Affinity Matrix in object segmentation and semantic segmentation tasks. Our code is available at https://github.com/chandagrover/SimSAM.

arXiv:2406.07895

Emotional Conversation: Empowering Talking Faces with Cohesive Expression, Gaze and Pose Generation

Vivid talking face generation holds immense potential applications across diverse multimedia domains, such as film and game production. While existing methods accurately synchronize lip movements with input audio, they typically ignore crucial alignments between emotion and facial cues, which include expression, gaze, and head pose. These alignments are indispensable for synthesizing realistic videos. To address these issues, we propose a two-stage audio-driven talking face generation framework that employs 3D facial landmarks as intermediate variables. This framework achieves collaborative alignment of expression, gaze, and pose with emotions through self-supervised learning. Specifically, we decompose this task into two key steps, namely speech-to-landmarks synthesis and landmarks-to-face generation. The first step focuses on simultaneously synthesizing emotionally aligned facial cues, including normalized landmarks that represent expressions, gaze, and head pose. These cues are subsequently reassembled into relocated facial landmarks. In the second step, these relocated landmarks are mapped to latent key points using self-supervised learning and then input into a pretrained model to create high-quality face images. Extensive experiments on the MEAD dataset demonstrate that our model significantly advances the state-of-the-art performance in both visual quality and emotional alignment.

arXiv:2406.08267공식 코드 · Papers with Code

A deep cut into Split Federated Self-supervised Learning

Collaborative self-supervised learning has recently become feasible in highly distributed environments by dividing the network layers between client devices and a central server. However, state-of-the-art methods, such as MocoSFL, are optimized for network division at the initial layers, which decreases the protection of the client data and increases communication overhead. In this paper, we demonstrate that splitting depth is crucial for maintaining privacy and communication efficiency in distributed training. We also show that MocoSFL suffers from a catastrophic quality deterioration for the minimal communication overhead. As a remedy, we introduce Momentum-Aligned contrastive Split Federated Learning (MonAcoSFL), which aligns online and momentum client models during training procedure. Consequently, we achieve state-of-the-art accuracy while significantly reducing the communication overhead, making MonAcoSFL more practical in real-world scenarios.

arXiv:2406.07900

Exploring Self-Supervised Multi-view Contrastive Learning for Speech Emotion Recognition with Limited Annotations

Recent advancements in Deep and Self-Supervised Learning (SSL) have led to substantial improvements in Speech Emotion Recognition (SER) performance, reaching unprecedented levels. However, obtaining sufficient amounts of accurately labeled data for training or fine-tuning the models remains a costly and challenging task. In this paper, we propose a multi-view SSL pre-training technique that can be applied to various representations of speech, including the ones generated by large speech models, to improve SER performance in scenarios where annotations are limited. Our experiments, based on wav2vec 2.0, spectral and paralinguistic features, demonstrate that the proposed framework boosts the SER performance, by up to 10% in Unweighted Average Recall, in settings with extremely sparse data annotations.

arXiv:2406.06872

Revolutionizing Wireless Networks with Self-Supervised Learning: A Pathway to Intelligent Communications

With the rapid proliferation of mobile devices and data, next-generation wireless communication systems face stringent requirements for ultra-low latency, ultra-high reliability, and massive connectivity. Traditional AI-driven wireless network designs, while promising, often suffer from limitations such as dependency on labeled data and poor generalization. To address these challenges, we present an integration of self-supervised learning (SSL) into wireless networks. SSL leverages large volumes of unlabeled data to train models, enhancing scalability, adaptability, and generalization. This paper offers a comprehensive overview of SSL, categorizing its application scenarios in wireless network optimization and presenting a case study on its impact on semantic communication. Our findings highlight the potentials of SSL to significantly improve wireless network performance without extensive labeled data, paving the way for more intelligent and efficient communication systems.

arXiv:2406.06643

Transforming Heart Chamber Imaging: Self-Supervised Learning for Whole Heart Reconstruction and Segmentation

Automated segmentation of Cardiac Magnetic Resonance (CMR) plays a pivotal role in efficiently assessing cardiac function, offering rapid clinical evaluations that benefit both healthcare practitioners and patients. While recent research has primarily focused on delineating structures in the short-axis orientation, less attention has been given to long-axis representations, mainly due to the complex nature of structures in this orientation. Performing pixel-wise segmentation of the left ventricular (LV) myocardium and the four cardiac chambers in 2-D steady-state free precession (SSFP) cine sequences is a crucial preprocessing stage for various analyses. However, the challenge lies in the significant variability in contrast, appearance, orientation, and positioning of the heart across different patients, clinical views, scanners, and imaging protocols. Consequently, achieving fully automatic semantic segmentation in this context is notoriously challenging. In recent years, several deep learning models have been proposed to accurately quantify and diagnose cardiac pathologies. These automated tools heavily rely on the accurate segmentation of cardiac structures in magnetic resonance images (MRI). Hence, there is a need for new methods to handle such structures' geometrical and textural complexities. We proposed 2D and 3D two-stage self-supervised deep learning segmentation hybrid transformer and CNN-based architectures for 4CH whole heart segmentation. Accurate segmentation of the ventricles and atria in 4CH views is crucial for analyzing heart health and reconstructing four-chamber meshes, which are essential for estimating various parameters to assess overall heart condition. Our proposed method outperformed state-of-the-art techniques, demonstrating superior performance in this domain.

arXiv:2406.05065

Emo-bias: A Large Scale Evaluation of Social Bias on Speech Emotion Recognition

The rapid growth of Speech Emotion Recognition (SER) has diverse global applications, from improving human-computer interactions to aiding mental health diagnostics. However, SER models might contain social bias toward gender, leading to unfair outcomes. This study analyzes gender bias in SER models trained with Self-Supervised Learning (SSL) at scale, exploring factors influencing it. SSL-based SER models are chosen for their cutting-edge performance. Our research pioneering research gender bias in SER from both upstream model and data perspectives. Our findings reveal that females exhibit slightly higher overall SER performance than males. Modified CPC and XLS-R, two well-known SSL models, notably exhibit significant bias. Moreover, models trained with Mandarin datasets display a pronounced bias toward valence. Lastly, we find that gender-wise emotion distribution differences in training data significantly affect gender bias, while upstream model representation has a limited impact.

arXiv:2406.06646

Emotion-Aware Speech Self-Supervised Representation Learning with Intensity Knowledge

Speech Self-Supervised Learning (SSL) has demonstrated considerable efficacy in various downstream tasks. Nevertheless, prevailing self-supervised models often overlook the incorporation of emotion-related prior information, thereby neglecting the potential enhancement of emotion task comprehension through emotion prior knowledge in speech. In this paper, we propose an emotion-aware speech representation learning with intensity knowledge. Specifically, we extract frame-level emotion intensities using an established speech-emotion understanding model. Subsequently, we propose a novel emotional masking strategy (EMS) to incorporate emotion intensities into the masking process. We selected two representative models based on Transformer and CNN, namely MockingJay and Non-autoregressive Predictive Coding (NPC), and conducted experiments on IEMOCAP dataset. Experiments have demonstrated that the representations derived from our proposed method outperform the original model in SER task.

arXiv:2406.07163

FaceGPT: Self-supervised Learning to Chat about 3D Human Faces

We introduce FaceGPT, a self-supervised learning framework for Large Vision-Language Models (VLMs) to reason about 3D human faces from images and text. Typical 3D face reconstruction methods are specialized algorithms that lack semantic reasoning capabilities. FaceGPT overcomes this limitation by embedding the parameters of a 3D morphable face model (3DMM) into the token space of a VLM, enabling the generation of 3D faces from both textual and visual inputs. FaceGPT is trained in a self-supervised manner as a model-based autoencoder from in-the-wild images. In particular, the hidden state of LLM is projected into 3DMM parameters and subsequently rendered as 2D face image to guide the self-supervised learning process via image-based reconstruction. Without relying on expensive 3D annotations of human faces, FaceGPT obtains a detailed understanding about 3D human faces, while preserving the capacity to understand general user instructions. Our experiments demonstrate that FaceGPT not only achieves high-quality 3D face reconstructions but also retains the ability for general-purpose visual instruction following. Furthermore, FaceGPT learns fully self-supervised to generate 3D faces based on complex textual inputs, which opens a new direction in human face analysis.

arXiv:2406.07398

Visual Representation Learning with Stochastic Frame Prediction

Self-supervised learning of image representations by predicting future frames is a promising direction but still remains a challenge. This is because of the under-determined nature of frame prediction; multiple potential futures can arise from a single current frame. To tackle this challenge, in this paper, we revisit the idea of stochastic video generation that learns to capture uncertainty in frame prediction and explore its effectiveness for representation learning. Specifically, we design a framework that trains a stochastic frame prediction model to learn temporal information between frames. Moreover, to learn dense information within each frame, we introduce an auxiliary masked image modeling objective along with a shared decoder architecture. We find this architecture allows for combining both objectives in a synergistic and compute-efficient manner. We demonstrate the effectiveness of our framework on a variety of tasks from video label propagation and vision-based robot learning domains, such as video segmentation, pose tracking, vision-based robotic locomotion, and manipulation tasks. Code is available on the project webpage: https://sites.google.com/view/2024rsp.

arXiv:2406.06479

Graph-Based Bidirectional Transformer Decision Threshold Adjustment Algorithm for Class-Imbalanced Molecular Data

Data sets with imbalanced class sizes, where one class size is much smaller than that of others, occur exceedingly often in many applications, including those with biological foundations, such as disease diagnosis and drug discovery. Therefore, it is extremely important to be able to identify data elements of classes of various sizes, as a failure to do so can result in heavy costs. Nonetheless, many data classification procedures do not perform well on imbalanced data sets as they often fail to detect elements belonging to underrepresented classes. In this work, we propose the BTDT-MBO algorithm, incorporating Merriman-Bence-Osher (MBO) approaches and a bidirectional transformer, as well as distance correlation and decision threshold adjustments, for data classification tasks on highly imbalanced molecular data sets, where the sizes of the classes vary greatly. The proposed technique not only integrates adjustments in the classification threshold for the MBO algorithm in order to help deal with the class imbalance, but also uses a bidirectional transformer procedure based on an attention mechanism for self-supervised learning. In addition, the model implements distance correlation as a weight function for the similarity graph-based framework on which the adjusted MBO algorithm operates. The proposed method is validated using six molecular data sets and compared to other related techniques. The computational experiments show that the proposed technique is superior to competing approaches even in the case of a high class imbalance ratio.

arXiv:2406.06305

NeuroMoCo: A Neuromorphic Momentum Contrast Learning Method for Spiking Neural Networks

Recently, brain-inspired spiking neural networks (SNNs) have attracted great research attention owing to their inherent bio-interpretability, event-triggered properties and powerful perception of spatiotemporal information, which is beneficial to handling event-based neuromorphic datasets. In contrast to conventional static image datasets, event-based neuromorphic datasets present heightened complexity in feature extraction due to their distinctive time series and sparsity characteristics, which influences their classification accuracy. To overcome this challenge, a novel approach termed Neuromorphic Momentum Contrast Learning (NeuroMoCo) for SNNs is introduced in this paper by extending the benefits of self-supervised pre-training to SNNs to effectively stimulate their potential. This is the first time that self-supervised learning (SSL) based on momentum contrastive learning is realized in SNNs. In addition, we devise a novel loss function named MixInfoNCE tailored to their temporal characteristics to further increase the classification accuracy of neuromorphic datasets, which is verified through rigorous ablation experiments. Finally, experiments on DVS-CIFAR10, DVS128Gesture and N-Caltech101 have shown that NeuroMoCo of this paper establishes new state-of-the-art (SOTA) benchmarks: 83.6% (Spikformer-2-256), 98.62% (Spikformer-2-256), and 84.4% (SEW-ResNet-18), respectively.

arXiv:2406.05796

ProFeAT: Projected Feature Adversarial Training for Self-Supervised Learning of Robust Representations

The need for abundant labelled data in supervised Adversarial Training (AT) has prompted the use of Self-Supervised Learning (SSL) techniques with AT. However, the direct application of existing SSL methods to adversarial training has been sub-optimal due to the increased training complexity of combining SSL with AT. A recent approach, DeACL, mitigates this by utilizing supervision from a standard SSL teacher in a distillation setting, to mimic supervised AT. However, we find that there is still a large performance gap when compared to supervised adversarial training, specifically on larger models. In this work, investigate the key reason for this gap and propose Projected Feature Adversarial Training (ProFeAT) to bridge the same. We show that the sub-optimal distillation performance is a result of mismatch in training objectives of the teacher and student, and propose to use a projection head at the student, that allows it to leverage weak supervision from the teacher while also being able to learn adversarially robust representations that are distinct from the teacher. We further propose appropriate attack and defense losses at the feature and projector, alongside a combination of weak and strong augmentations for the teacher and student respectively, to improve the training data diversity without increasing the training complexity. Through extensive experiments on several benchmark datasets and models, we demonstrate significant improvements in both clean and robust accuracy when compared to existing SSL-AT methods, setting a new state-of-the-art. We further report on-par/ improved performance when compared to TRADES, a popular supervised-AT method.

arXiv:2406.05686

Provable Optimization for Adversarial Fair Self-supervised Contrastive Learning

This paper studies learning fair encoders in a self-supervised learning (SSL) setting, in which all data are unlabeled and only a small portion of them are annotated with sensitive attribute. Adversarial fair representation learning is well suited for this scenario by minimizing a contrastive loss over unlabeled data while maximizing an adversarial loss of predicting the sensitive attribute over the data with sensitive attribute. Nevertheless, optimizing adversarial fair representation learning presents significant challenges due to solving a non-convex non-concave minimax game. The complexity deepens when incorporating a global contrastive loss that contrasts each anchor data point against all other examples. A central question is ``{\it can we design a provable yet efficient algorithm for solving adversarial fair self-supervised contrastive learning}?'' Building on advanced optimization techniques, we propose a stochastic algorithm dubbed SoFCLR with a convergence analysis under reasonable conditions without requring a large batch size. We conduct extensive experiments to demonstrate the effectiveness of the proposed approach for downstream classification with eight fairness notions.

arXiv:2406.05308공식 코드 · Papers with Code

Weakly Supervised Set-Consistency Learning Improves Morphological Profiling of Single-Cell Images

Optical Pooled Screening (OPS) is a powerful tool combining high-content microscopy with genetic engineering to investigate gene function in disease. The characterization of high-content images remains an active area of research and is currently undergoing rapid innovation through the application of self-supervised learning and vision transformers. In this study, we propose a set-level consistency learning algorithm, Set-DINO, that combines self-supervised learning with weak supervision to improve learned representations of perturbation effects in single-cell images. Our method leverages the replicate structure of OPS experiments (i.e., cells undergoing the same genetic perturbation, both within and across batches) as a form of weak supervision. We conduct extensive experiments on a large-scale OPS dataset with more than 5000 genetic perturbations, and demonstrate that Set-DINO helps mitigate the impact of confounders and encodes more biologically meaningful information. In particular, Set-DINO recalls known biological relationships with higher accuracy compared to commonly used methods for morphological profiling, suggesting that it can generate more reliable insights from drug target discovery campaigns leveraging OPS.

arXiv:2406.04853

Time-Series JEPA for Predictive Remote Control under Capacity-Limited Networks

In remote control systems, transmitting large data volumes (e.g. video feeds) from wireless sensors to faraway controllers is challenging when the uplink channel capacity is limited (e.g. RedCap devices or massive wireless sensor networks). Furthermore, the controllers often only need the information-rich components of the original data. To address this, we propose a Time-Series Joint Embedding Predictive Architecture (TS-JEPA) and a semantic actor trained through self-supervised learning. This approach harnesses TS-JEPA's semantic representation power and predictive capabilities by capturing spatio-temporal correlations in the source data. We leverage this to optimize uplink channel utilization, while the semantic actor calculates control commands directly from the encoded representations, rather than from the original data. We test our model through multiple parallel instances of the well-known inverted cart-pole scenario, where the approach is validated through the maximization of stability under constrained uplink channel capacity.

arXiv:2406.04997

On the social bias of speech self-supervised models

Self-supervised learning (SSL) speech models have achieved remarkable performance in various tasks, yet the biased outcomes, especially affecting marginalized groups, raise significant concerns. Social bias refers to the phenomenon where algorithms potentially amplify disparate properties between social groups present in the data used for training. Bias in SSL models can perpetuate injustice by automating discriminatory patterns and reinforcing inequitable systems. This work reveals that prevalent SSL models inadvertently acquire biased associations. We probe how various factors, such as model architecture, size, and training methodologies, influence the propagation of social bias within these models. Finally, we explore the efficacy of debiasing SSL models through regularization techniques, specifically via model compression. Our findings reveal that employing techniques such as row-pruning and training wider, shallower models can effectively mitigate social bias within SSL model.

arXiv:2406.04942

Joint Spatial-Temporal Modeling and Contrastive Learning for Self-supervised Heart Rate Measurement

This paper briefly introduces the solutions developed by our team, HFUT-VUT, for Track 1 of self-supervised heart rate measurement in the 3rd Vision-based Remote Physiological Signal Sensing (RePSS) Challenge hosted at IJCAI 2024. The goal is to develop a self-supervised learning algorithm for heart rate (HR) estimation using unlabeled facial videos. To tackle this task, we present two self-supervised HR estimation solutions that integrate spatial-temporal modeling and contrastive learning, respectively. Specifically, we first propose a non-end-to-end self-supervised HR measurement framework based on spatial-temporal modeling, which can effectively capture subtle rPPG clues and leverage the inherent bandwidth and periodicity characteristics of rPPG to constrain the model. Meanwhile, we employ an excellent end-to-end solution based on contrastive learning, aiming to generalize across different scenarios from complementary perspectives. Finally, we combine the strengths of the above solutions through an ensemble strategy to generate the final predictions, leading to a more accurate HR estimation. As a result, our solutions achieved a remarkable RMSE score of 8.85277 on the test dataset, securing \textbf{2nd place} in Track 1 of the challenge.